© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34368
    Prev
    Next
    INDEX
    Explanations

    creating or initializing objects

    np_acts-logits-general · gemini-2.5-flash-lite

    variable initialization and assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     firme
    0.49
     படங்கள்
    0.46
     pension
    0.40
     gira
    0.40
     garder
    0.39
    痠
    0.39
     dü
    0.38
    ಟ್
    0.38
    라운
    0.38
    पाला
    0.38
    POSITIVE LOGITS
    填写
    0.49
    ViewController
    0.45
     ViewController
    0.44
    Enterprise
    0.42
     назнача
    0.41
    聿
    0.40
    obox
    0.39
    Bean
    0.39
    赋值
    0.39
     Bean
    0.38
    Activations Density 0.002%

    No Known Activations